Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, but the description adds value beyond that by disclosing what gets destroyed ('delivery ledger') and that the operation cannot be undone. This gives the agent the consequence profile (cascade deletion of ledger data) that the boolean annotation alone cannot express. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero filler. 'Delete' is front-loaded, 'Permanently' immediately sets the critical constraint, and the standalone 'Irreversible.' fragment lands the most important warning. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter destructive tool with destructiveHint already annotated, this is nearly complete: it names the target, the collateral damage (delivery ledger), and the irreversibility. The only gaps are minor — no mention of error behavior for a nonexistent binding_id or success/failure signalling — but nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% — binding_id is already documented as 'Id of the partner binding to delete.' The description adds marginal context by revealing the consequence of that parameter (the ledger goes with it), but it provides no format, validation, or lookup details beyond the schema. Baseline 3 is appropriate given full schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('delete') and resource ('partner binding'), and goes further by scoping the effect to 'its delivery ledger' — a detail that distinguishes this hard-delete from soft-state siblings like set_partner_binding_status or update_partner_binding. The 'Irreversible' qualifier reinforces that this is a permanent removal, not a toggle.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The permanence framing ('Permanently delete', 'Irreversible') implies when to use this tool versus reversible alternatives, but the description never names a sibling such as set_partner_binding_status for temporary deactivation. The usage context is clear but strictly implied; no explicit exclusions or alternative routing is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.